Skip to main content
AITier

Qwen3.8 Max

AlibabaQwenOpen WeightQwen3.8-Max License · Commercial OK

Description

Qwen3.8 Max, released as the Qwen3.8-2.4T-A95B open-weight checkpoint, is Qwen's flagship mixture-of-experts model for coding, research, professional workflows, and long-horizon agents. It has 2.4 trillion total parameters with 95 billion active parameters, a native 262,144-token context window extensible to about 1 million tokens, and always-on thinking. QwenCloud serves the same model in the Qwen3.8 Max API family with text and image input.

Release Date
2026-08-03
Parameters
2.4T
Context Length
1.0M
Modalities
image, pdf, text, video

Capability Radar

55
general
69
coding
93
reasoning
69
science
60
agents
90
multimodal

Rankings

Domain#RankScoreSource
Agentic Capability4
79.0
LS
Code Ranking26
91.0
AA
General Ranking8
92.0
AA
Math Reasoning17
91.0
LB
Multimodal Ranking10
65.0
LS
Reasoning13
88.0
LB
Science26
87.0
AA

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Agents

QwenReactBench1724.00 / 2000SR
QwenSVG1713.00 / 2000SR
PaperBench93.0%SR
Terminal-Bench 2.186.6%SR
OSWorld-Verified86.1%SR
AndroidWorld85.3%SR
WideSearch81.9%SR
QwenSWEBench80.7%SR
MobileWorld77.8%SR
AndroidBench75.1%SR
CoWorkBench74.8%SR
FrontierSWE73.5%SR
Toolathlon72.5%SR
SkillsBench70.2%SR
Workspace Bench67.7%SR
SWE-Bench ProPrinceton NLP (2024)67.7%SR
QwenQoderBench58.4%SR
DeepSWE 1.156.6%SR
NL2Repo55.9%SR
Job Bench53.4%SR
OneMillion Bench52.5%SR
Agents' Last Exam52.4%SR
MLS-Bench Lite41.0%SR
AutomationBench27.3%SR

Biology

GPQANYU + Cohere + Anthropic (2023)92.6%SR

Code

Vision2Web69.0%SR

Finance

PRBench-Finance58.3%SR

General

MRCR v2 (8-needle)92.9%SR
IFBench82.8%SR
MMMU-Pro82.3%SR
LongBench v266.3%SR

Grounding

ScreenSpot Pro84.5%SR

Healthcare

HealthBench60.2%SR

Knowledge

PLawBench73.2%SR
PRBench-Legal57.6%SR

Long Context

LVBench81.8%SR

Math

Humanity's Last Exam (with tools, text-only)56.2%SR
Humanity's Last Exam43.6%SR

Multimodal

VideoMME w sub.90.4%SR
PerceptionBench63.5%SR

Reasoning

ERQA77.8%SR

Spatial Reasoning

RealWorldQA88.0%SR

AA Evaluation Indices

(Artificial Analysis)
Coding Index(Artificial Analysis)
71.8
Intelligence Index(Artificial Analysis)
58.1
Gpqa(NYU + Cohere + Anthropic (2023))
0.9
Terminalbench V2 1
0.8
Lcr(Artificial Analysis)
0.7
Scicode(UIUC + Argonne National Lab (2024))
0.5
Tau Banking
0.5
Hle(Center for AI Safety + Scale AI (2025))
0.4

LLM Stats Category Scores

(LLM Stats (zeroeval))
Physics
90
Biology
90
Chemistry
90
Video
90
Multimodal
80
Search
80
Spatial Reasoning
80
Instruction Following
80
Grounding
80
Vision
80
Long Context
70
Reasoning
70
Structured Output
70
General
70
Agents
70
Code
70
Productivity
60
Healthcare
60
Tool Calling
60
Math
50

Pricing

Input Price$2 / 1M tokens
Output Price$6 / 1M tokens
Blended Price (3:1)$3 / 1M tokens
Cache Read Price$0.25 / 1M tokens
Cache Write Price$2.5 / 1M tokens

Speed

Tokens/sec45.2
Time to First Token1.95s
Time to Answer46.22s

Provider Price Ranking

Provider Price Ranking

13 providers

Cheapest: AIHubMixMost Expensive: Charm Hyper
ProviderInputOutput
1AIHubMixCheapest
$1.69
$5.07
2Alibaba (China)
$1.77744
$5.33231
3LLM Gateway
$1.815
$5.4461
4CrossModel
$1.88
$5.63
5AlibabaPRIMARY
$2
$6
6NanoGPT
$2
$6
7OpenRouter
$2
$6
8OpenCode Go
$2
$6
9Kilo Gateway
$2
$6
10DigitalOcean
$2
$6
11Merge Gateway
$2
$6
12EmpirioLabs AI
$2
$6
13Charm Hyper
$2
$6

Compare pricing across different API providers for this model.

External Sources

LLM StatsArtificial Analysis